INDEX

Explanations

descriptive adjectives related to size and spatial characteristics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Nevermind

-0.43

companyname

-0.42

 esas

-0.42

Zobacz

-0.42

Vezi

-0.41

 MotionEvent

-0.41

Berikut

-0.41

Здравствуйте

-0.40

ρη

-0.40

ին

-0.40

POSITIVE LOGITS

adaptiveStyles

0.70

Попис

0.70

IndentedString

0.69

msgTypes

0.67

 Secondary

0.62

 wrought

0.61

contentLoaded

0.61

writeFieldEnd

0.60

 متعلقه

0.60

 يتيمه

0.60

Activations Density 0.001%

descriptive adjectives related to size and spatial characteristics

No Comments

No Known Activations